2026-09-20T08:55:42Zhttps://dspace.mit.edu/server/oai/requestoai:dspace.mit.edu:1721.1/1230672026-06-06T00:55:16Zcom_1721.1_7582com_1721.1_7581col_1721.1_131023
Aleksander Ma̧dry.
Zeng, Brandon.
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science.
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
2019-11-22T00:09:30Z
2019-11-22T00:09:30Z
2019
2019
https://hdl.handle.net/1721.1/123067
1127292128
Thesis: M. Eng., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2019
Cataloged from PDF version of thesis.
Includes bibliographical references (page 37).
Residual networks (ResNets) are now a prominent architecture in the field of deep learning. However, an explanation for their success remains elusive. The original view is that residual connections allows for the training of deeper networks, but it is not clear that added layers are always useful, or even how they are used. In this work, we find that residual connections distribute learning behavior across layers, allowing resnets to indeed effectively use deeper layers and outperform standard networks. We support this explanation with results for network gradients and representation learning that show that residual connections make the training of individual residual blocks easier.
by Brandon Zeng.
M.Eng.
M.Eng. Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science
37 pages
eng
Massachusetts Institute of Technology
MIT theses are protected by copyright. They may be viewed, downloaded, or printed from this source but further reproduction or distribution in any format is prohibited without written permission.
http://dspace.mit.edu/handle/1721.1/7582
Electrical Engineering and Computer Science.
Towards understanding residual neural networks
Thesis
application/pdf
2019-11-22T00:09:29Z
Publication
Master
EECS
unknown
unknown
<Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="9a6390fd-8777-4e3f-887f-5e5abfeb57d4">
<Type xmlns="https://www.openaire.eu/cerif-profile/vocab/COAR_Publication_Types">http://purl.org/coar/resource_type/c_1843</Type>
<Language>eng</Language>
<Title>Towards understanding residual neural networks</Title>
<PublishedIn>
<Publication>
</Publication>
</PublishedIn>
<PublicationDate>2019</PublicationDate>
<Authors>
<Author>
<DisplayName>Zeng, Brandon.</DisplayName>
<Affiliation>
<OrgUnit>
</OrgUnit>
</Affiliation>
</Author>
</Authors>
<Editors>
</Editors>
<Publishers>
<Publisher>
<DisplayName>Massachusetts Institute of Technology</DisplayName>
<OrgUnit />
</Publisher>
</Publishers>
<License>http://dspace.mit.edu/handle/1721.1/7582</License>
<Keyword>Electrical Engineering and Computer Science.</Keyword>
<Abstract>Residual networks (ResNets) are now a prominent architecture in the field of deep learning. However, an explanation for their success remains elusive. The original view is that residual connections allows for the training of deeper networks, but it is not clear that added layers are always useful, or even how they are used. In this work, we find that residual connections distribute learning behavior across layers, allowing resnets to indeed effectively use deeper layers and outperform standard networks. We support this explanation with results for network gradients and representation learning that show that residual connections make the training of individual residual blocks easier.</Abstract>
<Access xmlns="http://purl.org/coar/access_right"
>
</Access>
</Publication>